• Journal of the Society of Disaster Information
• /
• v.18 no.1
• /
• pp.146-153
• /
• 2022

Purpose: In the case of domestic port facilities, port structures that have been in use for a long time have many problems in terms of safety performance and functionality due to the enlargement of ships, increased frequency of use, and the effects of natural disasters due to climate change. A big data analysis method was studied to develop an approximate model that can predict the aging pattern of a port facility based on the maintenance history data of the port facility. Method: In this study, member-level maintenance history data for caisson-type quay walls were collected, defined as big data, and based on the data, a predictive approximation model was derived to estimate the aging pattern and deterioration of the facility at the project level. A state-based aging pattern prediction model generated through Gaussian process (GP) and linear interpolation (SLPT) techniques was proposed, and models suitable for big data utilization were compared and proposed through validation. Result: As a result of examining the suitability of the proposed method, the SLPT method has RMSE of 0.9215 and 0.0648, and the predictive model applied with the SLPT method is considered suitable. Conclusion: Through this study, it is expected that the study of predicting performance degradation of big data-based facilities will become an important system in decision-making regarding maintenance.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.39-57
• /
• 2022

This paper proposes the GMOPTBoost algorithm to improve the performance of the AdaBoost algorithm for bankruptcy prediction in which class imbalance problem is inherent. AdaBoost algorithm has the advantage of providing a robust learning opportunity for misclassified samples. However, there is a limitation in addressing class imbalance problem because the concept of arithmetic mean accuracy is embedded in AdaBoost algorithm. GMOPTBoost can optimize the geometric mean accuracy and effectively solve the category imbalance problem by applying Gaussian gradient descent. The samples are constructed according to the following two phases. First, five class imbalance datasets are constructed to verify the effect of the class imbalance problem on the performance of the prediction model and the performance improvement effect of GMOPTBoost. Second, class balanced data are constituted through data sampling techniques to verify the performance improvement effect of GMOPTBoost. The main results of 30 times of cross-validation analyzes are as follows. First, the class imbalance problem degrades the performance of ensembles. Second, GMOPTBoost contributes to performance improvements of AdaBoost ensembles trained on imbalanced datasets. Third, Data sampling techniques have a positive impact on performance improvement. Finally, GMOPTBoost contributes to significant performance improvement of AdaBoost ensembles trained on balanced datasets.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.99-107
• /
• 2024

While the demand for extrapolating video content horizontally or vertically is increasing, even the most advanced techniques cannot successfully extrapolate all videos. Therefore, it is important to determine if a given video can be well extrapolated before attempting the actual extrapolation. This can help avoid wasting computing resources. This paper proposes a video classifier that can identify if a video is suitable for horizontal extrapolation. The classifier utilizes optical flow and an adaptive Gaussian blur network, which can be applied to flow-based video extrapolation methods. The labeling for training was rigorously conducted through user tests and quantitative evaluations. As a result of learning from this labeled dataset, a network was developed to determine the extrapolation capability of a given video. The proposed classifier achieved much more accurate classification performance than methods that simply use the original video or fixed blur alone by effectively capturing the characteristics of the video through optical flow and adaptive Gaussian blur network. This classifier can be utilized in various fields in conjunction with automatic video extrapolation techniques for immersive viewing experiences.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.789-799
• /
• 2018

This article presents machine learning based approach on Big data to analyzing time series data for anomaly detection in such industrial complex system. Long Short-Term Memory (LSTM) network have been demonstrated to be improved version of RNN and have become a useful aid for many tasks. This LSTM based model learn the higher level temporal features as well as temporal pattern, then such predictor is used to prediction stage to estimate future data. The prediction error is the difference between predicted output made by predictor and actual in-coming values. An error-distribution estimation model is built using a Gaussian distribution to calculate the anomaly in the score of the observation. In this manner, we move from the concept of a single anomaly to the idea of the collective anomaly. This work can assist the monitoring and management of Smart Factory in minimizing failure and improving manufacturing quality.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.6
• /
• pp.1477-1484
• /
• 2015

With the growth of financial industry with smartphone, interest on user authentication using smartphone has been arisen in these days. There are various type of biometric user authentication techniques, but gait recognition using accelerometer sensor in smartphone does not seem to develop remarkably. This paper suggests the method of user authentication using accelerometer sensor embedded in smartphone. Specifically, calibrate the sensor data from smartphone with 3D-transformation, extract features from transformed data and do principle component analysis, and learn model with using gaussian mixture model. Next, authenticate user data with confidence interval of GMM model. As result, proposed method is capable of user authentication with accelerometer sensor on smartphone as a high degree of accuracy(about 96%) even in the situation that environment control and limitation are minimum on the research.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.7 no.3
• /
• pp.132-136
• /
• 2014

We introduce a new architecture of TSK-based fuzzy inference system. The proposed model used fuzzy c-means clustering method(FCM) for efficient disposal of data. The premise part of fuzzy rules don't assume any membership function such as triangular, gaussian, ellipsoidal because we construct the premise part of fuzzy rules using FCM. As a result, we can reduce to architecture of model. In this paper, we are able to use four types of polynomials as consequence part of fuzzy rules such as simplified, linear, quadratic, modified quadratic. Weighed Least Square Estimator are used to estimates the coefficients of polynomial. The proposed model is evaluated with the use of Boston housing data called Machine Learning dataset.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.239-245
• /
• 2014

In this paper, a weighted value wrinkle detection method is suggested based on the analysis on the entire facial features such as face contour, face size, eyes and ears. Firstly, the main facial elements are detected with AAM method entirely from the input screen images. Such elements are mainly composed of shape-based and appearance methods. These are used for learning the facial model and for matching the face from new screen images based on the learned models. Secondly, the face and background are separated in the screen image. Four points with the biggest possibilities for wrinkling are selected from the face and high wrinkle weighted values are assigned to them. Finally, the wrinkles are detected by applying Canny edge algorithm for the interested points of weighted value. The suggested algorithm adopts various screen images for experiment. The experiments display the excellent results of face and wrinkle detection in the most of the screen images.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.847-851
• /
• 2004

In the original mixture density network(MDN), which was introduced by Bishop and Nabney, the parameters of the conditional probability density function are represented by the output vector of a single multi-layer perceptron. Among the recent modification of the MDNs, there is the so-called modified mixture density network, in which each of the priors, conditional means, and covariances is represented via an independent multi-layer perceptron. In this paper, we consider a further simplification of the modified MDN, in which the conditional means are linear with respect to the input variable together with the development of the MATLAB program for the simplification. In this paper, we first briefly review the original mixture density network, then we also review the modified mixture density network in which independent multi-layer perceptrons play an important role in the learning for the parameters of the conditional probability, and finally present a further modification so that the conditional means are linear in the input. The applicability of the presented method is shown via an illustrative simulation example.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.37 no.3
• /
• pp.104-113
• /
• 2000

In this study, we propose facial image recognition based on wavelet transform and neural network. This algorithm is proposed by following processes. First, two gray level images is captured in constant illumination and, after removing input image noise using a gaussian filter, differential image is obtained between background and face input image, and this image has a process of erosion and dilation. Second, a mask is made from dilation image and background and facial image is divided by projecting the mask into face input image Then, characteristic area of square shape that consists of eyes, a nose, a mouth, eyebrows and cheeks is detected by searching the edge of divided face image. Finally, after characteristic vectors are extracted from performing discrete wavelet transform(DWT) of this characteristic area and is normalized, normalized vectors become neural network input vectors. And recognition processing is performed based on neural network learning. Simulation results show recognition rate of 100 % about learned image and 92% about unlearned image.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.2
• /
• pp.399-406
• /
• 2009

In this study, Polynomial Radial Basis Function Neural Network(pRBFNN) based on Fuzzy Inference System is designed and its parameters such as learning rate, momentum coefficient, and distributed weight (width of RBF) are optimized by means of Particle Swarm Optimization. The proposed model can be expressed as three functional module that consists of condition part, conclusion part, and inference part in the viewpoint of fuzzy rule formed in 'If-then'. In the condition part of pRBFNN as a fuzzy rule, input space is partitioned by defining kernel functions (RBFs). Here, the structure of kernel functions, namely, RBF is generated from HCM clustering algorithm. We use Gaussian type and Inverse multiquadratic type as a RBF. Besides these types of RBF, Conic RBF is also proposed and used as a kernel function. Also, in order to reflect the characteristic of dataset when partitioning input space, we consider the width of RBF defined by standard deviation of dataset. In the conclusion part, the connection weights of pRBFNN are represented as a polynomial which is the extended structure of the general RBF neural network with constant as a connection weights. Finally, the output of model is decided by the fuzzy inference of the inference part of pRBFNN. In order to evaluate the proposed model, nonlinear function with 2 inputs, waster water dataset and gas furnace time series dataset are used and the results of pRBFNN are compared with some previous models. Approximation as well as generalization abilities are discussed with these results.